Atomic Structure Optimization with Machine-Learning Enabled Interpolation between Chemical Elements

Sami Kaappa, Casper Larsen, Karsten Wedel Jacobsen*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

158 Downloads (Pure)

Abstract

We introduce a computational method for global optimization of structure and ordering in atomic systems. The method relies on interpolation between chemical elements, which is incorporated in a machine-learning structural fingerprint. The method is based on Bayesian optimization with Gaussian processes and is applied to the global optimization of Au-Cu bulk systems, Cu-Ni surfaces with CO adsorption, and Cu-Ni clusters. The method consistently identifies low-energy structures, which are likely to be the global minima of the energy. For the investigated systems with 23-66 atoms, the number of required energy and force calculations is in the range 3-75.

Original languageEnglish
Article number166001
JournalPhysical Review Letters
Volume127
Issue number16
Number of pages6
ISSN0031-9007
DOIs
Publication statusPublished - 2021

Bibliographical note

Funding Information:
We acknowledge support from the VILLUM Center for Science of Sustainable Fuels and Chemicals, which is funded by the VILLUM Fonden Research Grant (No. 9455).

Fingerprint

Dive into the research topics of 'Atomic Structure Optimization with Machine-Learning Enabled Interpolation between Chemical Elements'. Together they form a unique fingerprint.

Cite this